Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder

Xiangyuan Zhao; Brian Nutter

doi:10.1109/SSIAI.2016.7459184

Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder

Xiangyuan Zhao, Brian Nutter

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

In this paper, we propose an algorithm for a Content Based Image Retrieval (CBIR) system based on Wavelet Transformation and Deep Autoencoder (DAE). For the proposed algorithm, the image is first processed by wavelet transform and decomposed into wavelet coefficients. The wavelet coefficients then become the input for a multiple input multiple task deep autoencoder (MIMT-DAE). In our design, only the approximation coefficients (CA) and diagonal detail coefficients (CD) are used. The result of retrieval performance is tested on the MNIST handwriting data base. The testing results show that the combination of wavelet transformation and MIMT-DAE increases the performance of image retrieval for shape and texture compared to a traditional single input single task deep autoencoder with far fewer training parameters required.

Original language	English
Title of host publication	2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	97-100
Number of pages	4
ISBN (Electronic)	9781467399197
DOIs	https://doi.org/10.1109/SSIAI.2016.7459184
State	Published - Apr 25 2016
Event	IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Santa Fe, United States Duration: Mar 6 2016 → Mar 8 2016

Publication series

Name	Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume	2016-April

Conference

Conference	IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016
Country	United States
City	Santa Fe
Period	03/6/16 → 03/8/16

Keywords

CBIR
Deep Neural Network
Multiple Input Multiple Task Deep Autoencoder
Wavelet Transformation

Access to Document

10.1109/SSIAI.2016.7459184

Fingerprint Dive into the research topics of 'Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder'. Together they form a unique fingerprint.

Cite this

Zhao, X., & Nutter, B. (2016). Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder. In 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings (pp. 97-100). [7459184] (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation; Vol. 2016-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSIAI.2016.7459184

Zhao, Xiangyuan ; Nutter, Brian. / Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder. 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 97-100 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation).

@inproceedings{09f55064bfc247389f5ec5a47e26a74d,

title = "Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder",

abstract = "In this paper, we propose an algorithm for a Content Based Image Retrieval (CBIR) system based on Wavelet Transformation and Deep Autoencoder (DAE). For the proposed algorithm, the image is first processed by wavelet transform and decomposed into wavelet coefficients. The wavelet coefficients then become the input for a multiple input multiple task deep autoencoder (MIMT-DAE). In our design, only the approximation coefficients (CA) and diagonal detail coefficients (CD) are used. The result of retrieval performance is tested on the MNIST handwriting data base. The testing results show that the combination of wavelet transformation and MIMT-DAE increases the performance of image retrieval for shape and texture compared to a traditional single input single task deep autoencoder with far fewer training parameters required.",

keywords = "CBIR, Deep Neural Network, Multiple Input Multiple Task Deep Autoencoder, Wavelet Transformation",

author = "Xiangyuan Zhao and Brian Nutter",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; null ; Conference date: 06-03-2016 Through 08-03-2016",

year = "2016",

month = apr,

day = "25",

doi = "10.1109/SSIAI.2016.7459184",

language = "English",

series = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "97--100",

booktitle = "2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings",

}

Zhao, X & Nutter, B 2016, Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder. in 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings., 7459184, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, vol. 2016-April, Institute of Electrical and Electronics Engineers Inc., pp. 97-100, IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Santa Fe, United States, 03/6/16. https://doi.org/10.1109/SSIAI.2016.7459184

Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder. / Zhao, Xiangyuan; Nutter, Brian.

2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 97-100 7459184 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation; Vol. 2016-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder

AU - Zhao, Xiangyuan

AU - Nutter, Brian

PY - 2016/4/25

Y1 - 2016/4/25

N2 - In this paper, we propose an algorithm for a Content Based Image Retrieval (CBIR) system based on Wavelet Transformation and Deep Autoencoder (DAE). For the proposed algorithm, the image is first processed by wavelet transform and decomposed into wavelet coefficients. The wavelet coefficients then become the input for a multiple input multiple task deep autoencoder (MIMT-DAE). In our design, only the approximation coefficients (CA) and diagonal detail coefficients (CD) are used. The result of retrieval performance is tested on the MNIST handwriting data base. The testing results show that the combination of wavelet transformation and MIMT-DAE increases the performance of image retrieval for shape and texture compared to a traditional single input single task deep autoencoder with far fewer training parameters required.

AB - In this paper, we propose an algorithm for a Content Based Image Retrieval (CBIR) system based on Wavelet Transformation and Deep Autoencoder (DAE). For the proposed algorithm, the image is first processed by wavelet transform and decomposed into wavelet coefficients. The wavelet coefficients then become the input for a multiple input multiple task deep autoencoder (MIMT-DAE). In our design, only the approximation coefficients (CA) and diagonal detail coefficients (CD) are used. The result of retrieval performance is tested on the MNIST handwriting data base. The testing results show that the combination of wavelet transformation and MIMT-DAE increases the performance of image retrieval for shape and texture compared to a traditional single input single task deep autoencoder with far fewer training parameters required.

KW - CBIR

KW - Deep Neural Network

KW - Multiple Input Multiple Task Deep Autoencoder

KW - Wavelet Transformation

UR - http://www.scopus.com/inward/record.url?scp=84971349374&partnerID=8YFLogxK

U2 - 10.1109/SSIAI.2016.7459184

DO - 10.1109/SSIAI.2016.7459184

M3 - Conference contribution

AN - SCOPUS:84971349374

T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

SP - 97

EP - 100

BT - 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 6 March 2016 through 8 March 2016

ER -

Zhao X, Nutter B. Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder. In 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 97-100. 7459184. (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation). https://doi.org/10.1109/SSIAI.2016.7459184

Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this